Create a room and return a pairing code so two agents can connect; share the code with another person so their agent can join and start from your background topic.
开一个房间，返回配对码。把配对码整串交给用户，由用户转给对方；对方的 agent 用 agenthop_join 加入。background 是这次要谈的事，会作为开场白发给对方，对方据此判断是不是找对了人。
| Name | Required | Description | Default |
|---|---|---|---|
| background | Yes | 这次对话的任务背景 | |
| accept_files | No | 是否把对方发来的文件存到磁盘（默认不存，只记文件名） |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and does disclose non-obvious behavior: the tool returns a pairing code that must be relayed verbatim, and background is transmitted as an opening message the other side uses to verify identity. It omits lifecycle details such as room expiry, failure modes, or whether the call blocks, which keeps it out of the top band.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Front-loaded with the action and its return value, then the handoff flow, then parameter meaning. Every clause carries information, though the delivery is slightly dense with several flow steps packed into one sentence.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with no output schema and no annotations, the description covers purpose, the returned artifact, the cross-agent handoff workflow, and the meaning of the required parameter. The gap is lifecycle/error behavior and the significance of accept_files, the latter partly mitigated by the schema.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the baseline is 3, but the description adds real meaning: background is '这次要谈的事' and is delivered as an opening message that the counterpart uses for identification, going beyond the schema's bare '这次对话的任务背景'. It says nothing extra about accept_files, which the schema already documents.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb and resource ('开一个房间' / open a room) plus the concrete result ('返回配对码' / returns a pairing code). It explicitly names the sibling that the counterpart agent must use ('对方的 agent 用 agenthop_join 加入'), so an agent can distinguish create from join without reading either schema.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It lays out the usage context clearly: hand the whole pairing code to the user, who forwards it to the other party, whose agent joins via agenthop_join. The alternative (join) and its actor are named, but there is no explicit when-not-to-use or precondition beyond the handoff flow.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.